Analysis methods: Statistical analysis

 

Until 2005, the precision of radio audience indicators was estimated by formulae based on normality assumptions, which are not strictly verified in the case of empirical surveys with complex plans. In ...

Determining 'quality' in media research often assigns much influence to survey response rates. Increasing scientific evidence suggests a more sophisticated viewpoint about survey quality is needed. An ...

Michael Lieberman, president of Multivariate Solutions, explains how to calculate a performance index that can be used to simplify statistical data, and produce results that are easily understood and ...

Michael Lieberman, founder and president of Mutivariate Solutions, explains some of the most popular uses for the statistical optimisation tool - 'Totally Unduplicated Reach and Frequency' (TURF) anal ...

While there has been good progress in the past several years in the conceptualization and understanding of the determinants of satisfaction, analytic methods for understanding customer satisfaction ha ...

This paper initiates a discussion about respondent anonymity. Both from the side of the consumer as well as from the client, there are reasons to give the removal of anonymity from respondents some se ...

In a recent paper in this Journal, Simon Broadbent and Allan Smith reviewed various ways of analysing data that relate consumers’ purchases to their ad exposure. They conclude that the most appropriat ...

The story of the failure of the grandiose Ford Edsel is well known. A detail of the story is that, in the Boardroom (before the Edsel was launched), advertising consultant William Stephenson had been ...

Over the last decade there has been a notable change of emphasis in the statistical analysis of survey data. Increasingly, social science researchers are finding it informative to fit probability mode ...

This paper discussed multiple regression and its possible use in market research and marketing. It won the MRS Gold Medal in 1965. The first part of the paper describes the linear multiple regression ...

Examines correlation, asking whether it necessarily yields the ‘best fit’ and whether this concept in necessarily objective. Similarly, does the correlation procedure have any intrinsic power to predi ...

This article is a response to the Ansell, Harrison and Archibald paper ‘Identifying cross-selling opportunities, using lifestyle segmentation and survival analysis’, published in Marketing Intelligenc ...

Basing its findings on a 10,000+ database of behavioural and demographic data describing the UK customers of a major international insurance company, the paper demonstrates the successful use of lifes ...

The paper explores the problems of analysing quota data, with particular reference to public opinion surveys from the 1930s and 1940s. The relevant data collection techniques and their implications ar ...

Multiple imputation is a well-established technique for analysing data sets where there is missing data. If the imputation model is correct, the resulting estimates are consistent. Alternative methods ...

Latent class analysis (LCA) is a statistical tool for evaluating the error in categorical data when two or more repeated measurements of the same survey are available. The paper illustrates an applica ...

The use of the logit-probit model for constructing social measurement scales is explored by using 2 data sets. The first was specifically designed for scaling and consists of answers by 1,490 individ ...